© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13121
    Prev
    Next
    INDEX
    Explanations

    information related to user authentication and server settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.63
     snippetHide
    -0.54
    GTCX
    -0.50
     Paglinawan
    -0.48
    InputTagHelper
    -0.48
     initComponents
    -0.48
    PullParser
    -0.47
    таратура
    -0.46
     protoimpl
    -0.46
    andoah
    -0.43
    POSITIVE LOGITS
     StatefulWidget
    0.55
    #+#
    0.45
     StatelessWidget
    0.43
    parsedMessage
    0.38
    dafx
    0.37
     passwd
    0.37
     pwd
    0.36
    chown
    0.35
    Slf
    0.34
    méno
    0.34
    Activations Density 0.145%

    No Known Activations